Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '));↵↵
    -0.07
    slope
    -0.06
     Dare
    -0.06
     watching
    -0.06
     slide
    -0.06
     Achievement
    -0.06
     tanggal
    -0.06
    guns
    -0.06
     tongues
    -0.06
    stuff
    -0.06
    POSITIVE LOGITS
    ollision
    0.06
    _Create
    0.06
     bilgileri
    0.06
    Türk
    0.06
    ριος
    0.06
     вас
    0.06
     programas
    0.06
     نظام
    0.06
     кноп
    0.06
     byte
    0.06
    Act Density 0.094%

    No Known Activations